2823 Model Context Protocol servers — searchable, rated, ready to install.
Score pages against 11,485 public taxonomy categories by embedding similarity. $0.05/call via MCP.
Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.
Ask Claude or ChatGPT about your own crypto trading: performance, patterns and behaviour.
Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.
Deterministic PC no-boot/no-POST diagnostics: real beep-code tables, no LLM guessing.
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
Local, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.
Official Korean apartment sale prices (MOLIT). Clean JSON, data global models cannot know — paid pe…
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Self-hosted MCP gateway and LLM proxy: OAuth 2.1, model aliases, Grok subscription as an API.
Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
LLM Orchestration Agent 2
Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.
Academic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.
Shared project memory for Claude Code, Codex and Cursor: decisions and corrections through MCP.
Indexed note: numbers, capitalised names, file names. Local, no model, no meaning check.
Premium agentic endpoint for default-probability-model-mcp.
Premium agentic endpoint for carbon-aware-inference-router-mcp.
Manage Marzban panels through the Model Context Protocol.
Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
Get a used car's market-price range (min/max/median) by model and year from carsensor.net.
Persistent, outcome-grounded episodic memory for Claude. 14ms CPU retrieval, no GPU, no vector DB.
Build and monitor LLM apps on Orq.ai: AI gateway, agents, prompts, evals, traces.
POST /mcp